© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111785
    Prev
    Next
    INDEX
    Explanations

    first name followed by last name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鼱
    -1.65
    了你
    -1.53
     your
    -1.53
    )
    -1.51
    嘞
    -1.49
     its
    -1.49
    -
    -1.46
     both
    -1.45
     certain
    -1.38
    犷
    -1.38
    POSITIVE LOGITS
    ↵↵
    2.16
    2
    1.49
    They
    1.47
    5
    1.47
     
    1.45
    9
    1.37
    ："
    1.36
    Because
    1.35
     seperti
    1.33
    3
    1.30
    Activations Density 0.056%

    No Known Activations